Krea 2 QuadView Character Turnaround Sheet
Turn a single reference image into a 4-panel character turnaround sheet — front, sides, and back of the same character, consistent across all four views — using the Krea 2 QuadView LoRA in ComfyUI. It's perfect for character design, consistent-character pipelines, 3D reference, and game/animation work where you need the same character from multiple angles.
✓ 100% free — download the workflow and run it locally.
Preview
Requirements
- NVIDIA RTX 30XX / 40XX / 50XX GPU
- CUDA-compatible GPU — see the VRAM guide above for which model fits your card (runs on 8 GB with the right GGUF quant)
- At least 20 GB free storage
Model downloads
- Alissonerdx https://huggingface.co/Alissonerdx
- Krea 2 Turbo GGUF – pick your quant https://huggingface.co/vantagewithai/Krea-2-Turbo-GGUF/tree/main
- Krea 2 Turbo FP8 – the workflow default https://huggingface.co/AlperKTS/Krea2_FP8/tree/main
- qwen3vl_4b_fp8_scaled.safetensors https://huggingface.co/Comfy-Org/Qwen3-VL/tree/main/text_encoders
- qwen_image_vae.safetensors https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae
- QuadView_krea2_v1.safetensors – Alissonerdx/CharacterSheet https://huggingface.co/Alissonerdx/CharacterSheet/tree/main
Custom nodes
- ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager
- ComfyUI-GGUF (for the GGUF loader path) https://github.com/city96/ComfyUI-GGUF
- ComfyUI-KJNodes https://github.com/kijai/ComfyUI-KJNodes
- rgthree-comfy https://github.com/rgthree/rgthree-comfy
Setup steps
- Download the free workflow .json with the button above.
- Download the 6 model file(s) listed above into their ComfyUI model folders.
- Install the 4 custom node(s) listed above via ComfyUI Manager, then fully restart ComfyUI.
- Drag the workflow .json onto the ComfyUI canvas and confirm each loader node has the right model selected.
- Run it. If a node shows red, update ComfyUI and restart before troubleshooting anything else.
Notes & tips
- Load the workflow and pick your model path — FP8 (default) or GGUF — using the Fast Groups Bypasser. If you switch to GGUF, load your chosen quant in the Unet Loader GGUF node.
- Load a clear reference image of your character through the Load Image node. Front-facing, full-body references give the cleanest turnarounds.
- Krea 2 Turbo runs at 10 steps, CFG 1.0. Step dial: 8 = stronger composition/instruction adherence, 12 = more face detail, 10 = balanced.
- Set the CLIPLoader type to krea2 or the text encoder won't work correctly.
- If you're using GGUF, make sure the ComfyUI-GGUF custom node is installed, or the Unet Loader GGUF node won't appear.
- Match the largest quant that fits your card — dropping unnecessarily low costs quality for VRAM you didn't need to save.
More resources
- https://www.patreon.com/TheLocalLab/posts/krea-2-image-in-162660487
- https://www.patreon.com/TheLocalLab/posts/krea-2-all-in-6-163760558
- https://www.locallabdigest.com/product-page/krea-2-image-model-in-stable-forge-ui-neo-6-gb-vram-one-click-installer
- Krea 2 RunPod Template https://get.runpod.io/Krea2-ComfyUI
Want the 1-click version?
Skip the manual model downloads and node installs — get a ready-to-run installer, or unlock all 80+ with Local Lab Pro.